Training in progress, step 500

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "gpt2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -33,7 +32,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.33.2",
+  "transformers_version": "4.52.4",
   "use_cache": true,
   "vocab_size": 50257
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfc68a678a7282f28f814f33be3347afd88f6d042bd588cb6398c81c72265141
+size 497774208

tokenizer_config.json

@@ -1,9 +1,21 @@
 {
   "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
   "bos_token": "<|endoftext|>",
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
   "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec3efa6718cac0964d992655f1d255bc52ca7af2930f0260cc3e18200153d8af
-size 4881
+oid sha256:0222dbd690708a6b9fbadc3717514b142bb650f7c8dda7d857d8cecd510f8c92
+size 5649